Application of Adaptive Wavelet Network for Power Quality Disturbance Recognition and Analysis

To improve power quality disturbance classification performance in distributed power system, a novel adaptive wavelet network based on wavelet transform and self-organizing learning array (SOLAR) system is proposed. The wavelet transform is useful in detecting and extracting signal features of various types of electric power quality disturbances because it is sensitive to signal irregularities. These feature vectors then are applied to SOLAR network for structure parameters training and disturbance pattern classification. By comparing with conventional neural network, it is concluded that SOLAR has better data driven learning and local interconnections performance. The research results between the proposed method and the other existing method are discussed. The simulation results demonstrate the proposed approach gives an effective way for improving classification accuracy of power quality disturbances.